PREVIEW. This is how it will look in an inbox; it was not sent to you. Each real email carries its own unsubscribe link and Keryn's postal address.

Keryn Headlines

Daily, Wednesday 1 October 2025 · Retrospective · Covers 30 September 2025 00:00 to 1 October 2025 00:00 UTC

Read on the web

Top developments

Critical WD My Cloud bug allows remote command injection

BleepingComputer · Advisory · Remediation

Researchers Disclose Google Gemini AI Flaws Allowing Prompt Injection and Cloud Exploits

The Hacker News · Research · AI Security, Remediation

Nearly 50,000 Cisco firewalls vulnerable to actively exploited flaws

BleepingComputer · Incident

SAST

Red Teaming Program Repair Agents: When Correct Patches can Hide Vulnerabilities

arXiv · Research · Agentic SDLC, Remediation, SAST

Agentic SDLC

Lita: Light Agent Uncovers the Agentic Coding Capabilities of LLMs

arXiv · Research · Agentic SDLC

Remediation

Chinese hackers exploiting VMware zero-day since October 2024

BleepingComputer · Analysis · Remediation

From Trace to Line: LLM Agent for Real-World OSS Vulnerability Localization

arXiv · Research · Remediation

SecureBERT 2.0: Advanced Language Model for Cybersecurity Intelligence

arXiv · Research · Remediation

Trust

SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From

arXiv · Research · Trust

Models

Direct Token Optimization: A Self-contained Approach to Large Language Model Unlearning

arXiv · Research · Models

SPATA: Systematic Pattern Analysis for Detailed and Transparent Data Cards

arXiv · Research · Models

Fairness Testing in Retrieval-Augmented Generation: How Small Perturbations Reveal Bias in Small Language Models

arXiv · Research · AI Security, Models

AI Security

CHAI: Command Hijacking against embodied AI

arXiv · Research · AI Security

Preventing Prompt Injection with Type-Directed Privilege Separation

arXiv · Research · AI Security

Microsoft Expands Sentinel Into Agentic Security Platform With Unified Data Lake

The Hacker News · Analysis · AI Security

Advisories in this window

  • 8 Maven advisories · 8 moderate
  • 7 npm advisories · 2 critical · 4 high · 1 moderate
  • 5 Go advisories · 4 high · 1 moderate
  • 1 NuGet advisory · 1 moderate
  • 1 Packagist advisory · 1 moderate

All advisories

Titles, links and short excerpts only; every item links to its source. Selection is automatic; the editor's note is AI-drafted and checked as described. Preview: the unsubscribe link and Keryn's postal address are added to each email when it is sent.